MRpro - open PyTorch-based MR reconstruction and processing package

TL;DR

MRpro is an open-source, PyTorch-based framework that streamlines MR image reconstruction and processing, supporting various acquisition types, algorithms, and deep learning components to enhance reproducibility and collaborative research.

Contribution

It introduces a comprehensive, extensible framework for MR reconstruction with unified data structures, a library of operators, and deep learning tools, promoting reproducibility and collaboration.

Findings

Demonstrates versatility across multiple MR acquisition methods

Supports motion correction and quantitative MR applications

Facilitates reproducible and collaborative MR research

Abstract

We introduce MRpro, an open-source image reconstruction package built upon PyTorch and open data formats. The framework comprises three main areas. First, it provides unified data structures for the consistent manipulation of MR datasets and their associated metadata (e.g., k-space trajectories). Second, it offers a library of composable operators, proximable functionals, and optimization algorithms, including a unified Fourier operator for all common trajectories and an extended phase graph simulation for quantitative MR. These components are used to create ready-to-use implementations of key reconstruction algorithms. Third, for deep learning, MRpro includes essential building blocks such as data consistency layers, differentiable optimization layers, and state-of-the-art backbone networks and integrates public datasets to facilitate reproducibility. MRpro is developed as a collaborative project supported by automated quality control. We demonstrate the versatility of MRpro across multiple applications, including Cartesian, radial, and spiral acquisitions; motion-corrected reconstruction; cardiac MR fingerprinting; learned spatially adaptive regularization weights; model-based learned image reconstruction and quantitative parameter estimation. MRpro offers an extensible framework for MR image reconstruction. With reproducibility and maintainability at its core, it facilitates collaborative development and provides a foundation for future MR imaging research.